You are on page 1of 12

VII.

MEASURE - PROBABILITY & STATISTICS

THERE IS ALWAYS A 100% PROBABILITY


THAT A PIECE OF TOAST WILL LAND
BUTTERED SIDE DOWN ON NEW CARPET.

FROM MURPHY'S LAWS

CSSGB 2014 VII - 1 QUALITY COUNCIL OF INDIANA


VII. MEASURE - PROBABILITY & STATISTICS BOK
PROBABILITY AND STATISTICS/BASIC CONCEPTS III.B.1

Probability and Statistics

Probability is described in the following topic areas:

C Probability and Statistics

C Basic Probability Concepts


C Central Limit Theorem

C Statistical Distributions

Basic Statistical Terms

Continuous Distributions containing infinite (variable) data points that may


Distributions be displayed on a continuous measurement scale. Examples:
normal, uniform, exponential, and Weibull distributions.
Discrete Distributions resulting from countable (attribute) data that has
Distributions a finite number of possible values. Examples: binomial,
Poisson, and hypergeometric distributions.
Decision Distribution used to make decisions and construct confidence
Distributions intervals. Examples: t, F, and chi-square distributions.
Parameter The true numeric population value, often unknown, estimated
by a statistic.
Population All possible observations of similar items from which a sample
is drawn.
Sample A randomly selected set of units or items drawn from a
population.
Statistic A numerical data value taken from a sample that may be used
to make an inference about a population.
(Omdahl, 2010)6

CSSGB 2014 VII - 2 QUALITY COUNCIL OF INDIANA


VII. MEASURE - PROBABILITY & STATISTICS BOK
PROBABILITY AND STATISTICS/BASIC CONCEPTS III.B.1

Drawing Valid Statistical Conclusions *


Analytical (Inferential) Studies

The objective of statistical inference is to draw conclusions about population


characteristics based on the information contained in a sample. Statistical inference
in a practical situation contains two elements: (1) the inference and (2) a measure
of its validity. The steps involved in statistical inference are:

C Define the problem objective precisely

C Decide if the problem will be evaluated by a one tail or two tail test

C Formulate a null hypothesis and an alternate hypothesis

C Select a test distribution and a critical value of the test statistic reflecting the
degree of uncertainty that can be tolerated (the alpha, , risk)

C Calculate a test statistic value from the sample information

C Make an inference about the population by comparing the calculated value to


the critical value. This step determines if the null hypothesis is to be rejected.
If the null is rejected, the alternate must be accepted.

C Communicate the findings to interested parties

Everyday, in our personal and professional lives, we are faced with decisions
between choice A or choice B. In most situations, relevant information is available;
but it may be presented in a form that is difficult to digest. Quite often, the data
seems inconsistent or contradictory. In these situations, an intuitive decision may
be little more than an outright guess.

While most people feel their intuitive powers are quite good, the fact is that
decisions made on gut-feeling are often wrong. The student should be aware that
the subjects of null hypothesis and types of errors are reviewed in Primer Section
IX.

* A substantial portion of the material throughout this Section comes from the CQE
Primer by Wortman (2012)10.

CSSGB 2014 VII - 3 QUALITY COUNCIL OF INDIANA


VII. MEASURE - PROBABILITY & STATISTICS BOK
PROBABILITY AND STATISTICS/BASIC CONCEPTS III.B.1

Drawing Valid Statistical Conclusions (Continued)


Enumeration (Descriptive) Studies

Enumerative data is data that can be counted. For example: the classification of
things, the classification of people into intervals of income, age or health. A census
is an enumerative collection and study. Useful tools for tests of hypothesis
conducted on enumerative data are the chi-square, binomial and Poisson
distributions.

Deming, in 1975, defined a contrast between enumeration and analysis:

Enumerative study A study in which action will be taken on the universe.

Analytic study A study in which action will be taken on a process to improve


performance in the future.

Descriptive Statistics

Numerical, descriptive measures create a mental picture of a set of data. These


measures calculated from a sample are numerical, descriptive measures called
statistics. When these measures describe a population, they are called parameters.

Measures Statistics Parameters


Mean X
Standard Deviation s

Table 7.1 Statistics and Parameters

Table 7.1 shows examples of statistics and parameters for the mean and standard
deviation. These two important measures are called central tendency and
dispersion.

Summary of Analytical and Enumerative Studies

Analytical studies start with the hypothesis statement made about population
parameters. A sample statistic is then used to test the hypothesis and either reject,
or fail to reject, the null hypothesis. At a stated level of confidence, one should then
be able to make inferences about the population.

CSSGB 2014 VII - 4 QUALITY COUNCIL OF INDIANA


VII. MEASURE - PROBABILITY & STATISTICS BOK
PROBABILITY AND STATISTICS/BASIC CONCEPTS III.B.2

Probability
Most quality theories use statistics to make inferences about a population based on
information contained in samples. The mechanism one uses to make these
inferences is probability. For a more expansive treatment of probability, see Triola
(1994)8 referenced at the end of this Section.

The probability of any event (E) lies between 0 and 1. The sum of the probabilities
of all possible events (E) in a sample space (S) = 1. The ratio of the chances favoring
an event to the total number of chances for and against the event. Probability (P) is
always a ratio.
Chances Favoring
P=
Chances Favoring Plus Chances Not Favoring

Simple Events
An event that cannot be decomposed is a simple event (E). The set of all sample
points for an experiment is called the sample space (S).

If an experiment is repeated a large number of times, (N), and the event (E) is
observed nE times, the probability of E is approximately:
nE
PE
N

Example 7.1: The probability of observing 3 on the toss of a single die is:
1
PE3 =
6

Example 7.2: What is the probability of getting 1, 2, 3, 4, 5, or 6 by throwing a die?

PET = P E1 + P E2 + P E3 + P E4 + P E5 + P E6
1 1 1 1 1 1
PET = + + + + + =1
6 6 6 6 6 6

CSSGB 2014 VII - 5 QUALITY COUNCIL OF INDIANA


VII. MEASURE - PROBABILITY & STATISTICS BOK
PROBABILITY AND STATISTICS/BASIC CONCEPTS III.B.2

Compound Events
Compound events are formed by a composition of two or more events. They consist
of more than one point in the sample space. For example, if two dice are tossed,
what is the probability of getting an 8? A die and a coin are tossed. What is the
probability of getting a 4 and tail? The two most important probability theorems are
the additive and multiplicative (covered later in this Section). For the following
discussion, EA = A and EB = B.

I. Composition. Consists of two possibilities -- a union or intersection.

A. Union of A and B.

If A and B are two events in a sample space (S), the union of A and B (A c B)
contains all sample points in event A or B or both.

Example 7.3: In the die toss of Example 7.2, consider the following:

If A = E1, E2 and E3 (numbers less than 4)


and B = E1, E3 and E5 (odd numbers), then A c B = E1, E2, E3 and E5.

B. Intersection of A and B.
If A and B are two events in a sample space (S), the intersection of A and B
(A 1 B) is composed of all sample points that are in both A and B.

Example 7.4: Refer to Example 7.3. A 1 B = E1 and E3

E4 E6 E4 E6
E2 E2
A A
S E1 E3 S E1 E3

E5 B E5 B

AcB A1B

Figure 7.2 Venn Diagrams Illustrating Union and Intersection

CSSGB 2014 VII - 6 QUALITY COUNCIL OF INDIANA


VII. MEASURE - PROBABILITY & STATISTICS BOK
PROBABILITY AND STATISTICS/BASIC CONCEPTS III.B.2

Compound Events (Continued)


II. Event Relationships. There are three relationships in finding the probability of
an event: complementary, conditional and mutually exclusive.

A. Complement of an Event.

The complement of an event A is all sample points in the sample space (S),
but not in A. The complement of A is 1-PA.

Example 7.5: If PA (cloudy days) is 0.3, the complement of A would be 1 - PA = 0.7


(clear).

PA = 0.3 1 - PA = 0.7

B. Conditional Probabilities.

The conditional probability of event A, given that B has occurred, is:


P A B
P A|B = if P B 0
P B

Example 7.6: If event A (rain) = 0.2, and event B (cloudiness) = 0.3, what is the
probability of rain on a cloudy day? (Note, it will not rain without clouds.)

P A B 0.2
P A|B = = = 0.67
P B 0.3
B = 0.3

Event A and B are said to be


independent if either: S A = 0.2

P(A|B) = P(A) or P(B|A) = P(B) However,


No Clouds = 0.7
P(A|B) = 0.67 and P(A) = 0.2 = no equality, and
P(B|A) = 1.00 and P(B) = 0.3 = no equality

Therefore, the events are said to be dependent.

CSSGB 2014 VII - 7 QUALITY COUNCIL OF INDIANA


VII. MEASURE - PROBABILITY & STATISTICS BOK
PROBABILITY AND STATISTICS/BASIC CONCEPTS III.B.2

Compound Events (Continued)


C. Mutually Exclusive Events.

If event A contains no sample points in common with event B, then they are
said to be mutually exclusive.

Example 7.7: Obtaining a 3 and a 2 on the toss of a single die is a mutually exclusive
event. The probability of observing both events simultaneously is zero. The
probability of obtaining either a 3 or a 2 is:
1 1 1
PE2 + PE3 = + =
6 6 3

D. Testing for Event Relationships.

Example 7.8: Refer to Example 7.3.

Event A: E1, E2, E3


Event B: E1, E3, E5

Are A and B mutually exclusive, complementary, independent, or dependent? A and


B contain two sample points in common so they are not mutually exclusive. They
are not complementary because B does not contain all points in S that are not in A.

To determine if they are independent requires a check.

Does P A|B = P A ?
P A B 2/6 2 1
P A|B = = = P A =
P B 1/2 3 2
Therefore P A|B P A

By definition, events A and B are dependent.

CSSGB 2014 VII - 8 QUALITY COUNCIL OF INDIANA


VII. MEASURE - PROBABILITY & STATISTICS BOK
PROBABILITY AND STATISTICS/BASIC CONCEPTS III.B.2

The Additive Law


If the two events are not mutually exclusive:

1. P (A c B) = P(A) + P(B) - P (A 1 B)

Note that P (A c B) is shown in many texts as P (A + B) and is read as the probability


of A or B.

Example 7.9: If one owns two cars and the probability of each car starting on a cold
morning is 0.7, what is the probability of getting to work?

P (A c B) = 0.7 + 0.7 - (0.7 x 0.7)


= 1.4 - 0.49
A AB B
= 0.91 = 91 %

If the two events are mutually exclusive, the law reduces to:

2. P (A c B) = P(A) + P(B) also P (A + B) = P(A) + P(B)

Example 7.10: If the probability of finding a black sock in a dark room is 0.4 and the
probability of finding a blue sock is 0.3, what is the chance of finding a blue or black
sock?

P (A c B) = 0.4 + 0.3 = 0.7 = 70 % Blue Black Red


0.3 0.4 0.3

Note: The problem statements center around the word or. Will car A or B start?
Will one get a black sock or blue sock?

CSSGB 2014 VII - 9 QUALITY COUNCIL OF INDIANA


VII. MEASURE - PROBABILITY & STATISTICS BOK
PROBABILITY AND STATISTICS/BASIC CONCEPTS III.B.2

The Multiplicative Law


If events A and B are dependent, the probability of A influences the probability of B.
This is known as conditional probability and the sample space is reduced.

For any two events A and B such that P(B) =/ 0,


P A B
1. P A|B = and P A B = P A|B P B
P B
Note, in some texts P(A 1 B) is shown as P(A C B) and is read as the probability of
A and B. P(B|A) is read as the probability of B given that A has occurred.

Example 7.11: If a shipment of 100 T.V. sets contains 30 defective units and two
samples are obtained, what is probability of finding both defective? (Event A is the
first sample and the sample space is reduced, and event B is the second sample.)

30 29 870
P A B = x = = 0.088
100 99 9900
P A B = 8.8 %

If events A and B are independent:

P (A 1 B) = P(A) X P(B)

Example 7.12: One relay in an electric circuit has a probability of working equal to
0.9. Another relay in series with the first has a chance of 0.8. What's the probability
that the circuit will work?

P (A 1 B) = 0.9 X 0.8 = 0.72


P (A 1 B) = 72%

Note: The problems center around the word and. Will T.V. A and B work? Will
relay A and B operate?

CSSGB 2014 VII - 10 QUALITY COUNCIL OF INDIANA


VII. MEASURE - PROBABILITY & STATISTICS BOK
PROBABILITY AND STATISTICS/CENTRAL LIMIT THEOREM III.B.2

Central Limit Theorem


If a random variable X has mean and finite variance 2, as n increases, X
approaches a normal distribution with mean and variance 2X . Where,
2X
2X = and n is the number of observations on which each mean is based.
n

Sampling Distribution of the Mean

Normal Distribution
of Sample Means

F(x)
Distribution of
Individuals


Figure 7.3 Distributions of Individuals Versus Means

The Central Limit Theorem States:

C The sample means (Xs) will be more normally distributed around than
individual readings (Xs). The distribution of sample means approaches
normal, regardless of the shape of the parent population. This is why X - R
control charts work!

C The spread in sample means (Xs) is less than Xs with the standard deviation
of Xs equal to the standard deviation of the population (individuals) divided
by the square root of the sample size. X is referred to as the standard error
of the mean:
s
X = X Which is estimated by sX = X
n n

Example 7.13: Assume the following are weight variation results: X = 20 grams and
s = 0.124 grams. Estimate X for a sample size of 4:
sX 0.124
Solution: sX = = = 0.062 grams
n 4

CSSGB 2014 VII - 11 QUALITY COUNCIL OF INDIANA


VII. MEASURE - PROBABILITY & STATISTICS BOK
PROBABILITY AND STATISTICS/CENTRAL LIMIT THEOREM III.B.2

Central Limit Theorem (Continued)


The significance of the central limit theorem on control charts is that the distribution
of sample means approaches a normal distribution. Refer to Figure 7.4 below:

Population Distribution Population Distribution Population Distribution Population Distribution

n=2 n=2
n=2
n=2

n=4 n=4
n=4 n=4

n = 25
n = 25 n = 25
n = 25

Sampling Distribution of X Sampling Distribution of X Sampling Distribution of X Sampling Distribution of X

Figure 7.4 Illustration of Central Tendency


(Lapin, 1982)5

In Figure 7.4, a variety of population distributions approach normality for the


sampling distribution of
X as n increases. For most distributions (but not all), a near
normal sampling distribution is attained with a sample size of 4 or 5.

CSSGB 2014 VII - 12 QUALITY COUNCIL OF INDIANA